Service interruption on Monday 11 July from 12:30 to 13:00: all the sites of the CCSD (HAL, EpiSciences, SciencesConf, AureHAL) will be inaccessible (network hardware connection).
Skip to Main content Skip to Navigation
Conference papers

Predicting Information Diffusion Patterns in Twitter

Abstract : The prediction of social media information propagation is a problem that has attracted a lot of interest over the recent years, especially because of the application of such predictions for effective marketing campaigns. Existing approaches have shown that the information cascades in social media are small and have a large width. We validate these results for Tree-Shaped Tweet Cascades created by the ReTweet action. The main contribution of our work is a methodology for predicting the information diffusion that will occur given a user’s tweet. We base our prediction on the linguistic features of the tweet as well as the user profile that created the initial tweet. Our results show that we can predict the Tweet-Pattern with good accuracy. Moreover, we show that influential networks within the Twitter graph tend to use different Tweet-Patterns.
Document type :
Conference papers
Complete list of metadata

Cited literature [18 references]  Display  Hide  Download
Contributor : Hal Ifip Connect in order to contact the contributor
Submitted on : Thursday, November 3, 2016 - 10:51:35 AM
Last modification on : Thursday, March 5, 2020 - 5:41:13 PM
Long-term archiving on: : Saturday, February 4, 2017 - 1:23:51 PM


Files produced by the author(s)


Distributed under a Creative Commons Attribution 4.0 International License



Eleanna Kafeza, Andreas Kanavos, Christos Makris, Pantelis Vikatos. Predicting Information Diffusion Patterns in Twitter. 10th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2014, Rhodes, Greece. pp.79-89, ⟨10.1007/978-3-662-44654-6_8⟩. ⟨hal-01391295⟩



Record views


Files downloads